Multilayered question answering system applied to temporality evaluation

Laburpena

This paper presents a multilayered Question Answering (QA) architecture suitable for enhancing current QA capabilities with the possibility of processing complex questions. That is, questions whose answer needs to be gathered from pieces of factual information that is scattered in different documents. Specifically, we have designed a specific layer oriented to process the different types of temporal questions. Complex temporal questions are first decomposed into simple questions, according to the temporal relations expressed in the original question. In the same way, the answers of each resulting simple question are recomposed, fulfilling the temporal restrictions of the original complex question. Using this architecture, a Temporal QA system has been developed. In this paper, we have been focused on explaining the last part of this process: the recomposition of the answers to the simple questions to obtain the final answer to the complex question. In addition, this unit has been evaluated using the previous decomposition that our system have made of TERQAS question corpus formed by 124 temporal questions. In order to obtain the answers to the simple questions we have used a general purpose QA system based on Web called IONAUT. Our system improves answering into a 34% of questions compared to a General Purpose QA system.